{"id":"https://openalex.org/W3199662914","doi":"https://doi.org/10.1109/asru51503.2021.9687971","title":"Beyond Isolated Utterances: Conversational Emotion Recognition","display_name":"Beyond Isolated Utterances: Conversational Emotion Recognition","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W3199662914","doi":"https://doi.org/10.1109/asru51503.2021.9687971","mag":"3199662914"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9687971","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9687971","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2109.06112","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040448607","display_name":"Raghavendra Pappagari","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2799853436","display_name":"Johns Hopkins Medicine","ror":"https://ror.org/037zgn354","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799853436"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raghavendra Pappagari","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University,Baltimore,MD,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University,Baltimore,MD,USA","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I2799853436"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027217976","display_name":"Piotr \u017belasko","orcid":"https://orcid.org/0000-0002-8245-0413"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2799853436","display_name":"Johns Hopkins Medicine","ror":"https://ror.org/037zgn354","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799853436"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Piotr Zelasko","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University,Baltimore,MD,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University,Baltimore,MD,USA","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I2799853436"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057010207","display_name":"Jes\u00fas Villalba","orcid":"https://orcid.org/0000-0001-9459-8426"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2799853436","display_name":"Johns Hopkins Medicine","ror":"https://ror.org/037zgn354","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799853436"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jesus Villalba","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University,Baltimore,MD,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University,Baltimore,MD,USA","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I2799853436"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069488212","display_name":"Laureano Moro-Vel\u00e1zquez","orcid":"https://orcid.org/0000-0002-3033-7005"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2799853436","display_name":"Johns Hopkins Medicine","ror":"https://ror.org/037zgn354","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799853436"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Laureano Moro-Velazquez","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University,Baltimore,MD,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University,Baltimore,MD,USA","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I2799853436"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050632169","display_name":"Najim Dehak","orcid":"https://orcid.org/0000-0002-4489-5753"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2799853436","display_name":"Johns Hopkins Medicine","ror":"https://ror.org/037zgn354","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799853436"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Najim Dehak","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University,Baltimore,MD,USA","Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University,Baltimore,MD,USA","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I2799853436"]},{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"39","last_page":"46"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.8094691634178162},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7597259283065796},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7408304214477539},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.614989161491394},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.586013913154602},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5640578866004944},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5209461450576782},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.43816155195236206},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4363013803958893},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4317755699157715},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4296644628047943},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08122766017913818},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.06956493854522705}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.8094691634178162},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7597259283065796},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7408304214477539},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.614989161491394},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.586013913154602},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5640578866004944},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5209461450576782},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.43816155195236206},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4363013803958893},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4317755699157715},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4296644628047943},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08122766017913818},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.06956493854522705},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/asru51503.2021.9687971","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9687971","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2109.06112","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2109.06112","pdf_url":"https://arxiv.org/pdf/2109.06112","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"doi:10.48550/arxiv.2109.06112","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2109.06112","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:3199662914","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2109.06112","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2109.06112","pdf_url":"https://arxiv.org/pdf/2109.06112","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5199999809265137,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3199662914.pdf","grobid_xml":"https://content.openalex.org/works/W3199662914.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W1973270182","https://openalex.org/W2031212775","https://openalex.org/W2055911634","https://openalex.org/W2061068689","https://openalex.org/W2138611879","https://openalex.org/W2146334809","https://openalex.org/W2147272821","https://openalex.org/W2158630797","https://openalex.org/W2399733683","https://openalex.org/W2408520939","https://openalex.org/W2578895956","https://openalex.org/W2805662932","https://openalex.org/W2889169802","https://openalex.org/W2941814890","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963686995","https://openalex.org/W2964300796","https://openalex.org/W2965453734","https://openalex.org/W2967714332","https://openalex.org/W2972818416","https://openalex.org/W2972944488","https://openalex.org/W2979826702","https://openalex.org/W3006475563","https://openalex.org/W3015489952","https://openalex.org/W3015707499","https://openalex.org/W3027687786","https://openalex.org/W3096147072","https://openalex.org/W3097973766","https://openalex.org/W3098824823","https://openalex.org/W3116016199","https://openalex.org/W3162890625","https://openalex.org/W4247286306","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6761563299"],"related_works":["https://openalex.org/W3010043419","https://openalex.org/W3010575424","https://openalex.org/W3116679303","https://openalex.org/W3157029782","https://openalex.org/W3120680448","https://openalex.org/W3116016199","https://openalex.org/W3203226213","https://openalex.org/W3160023107","https://openalex.org/W2755760886","https://openalex.org/W3016232306","https://openalex.org/W3169157361","https://openalex.org/W3005353736","https://openalex.org/W2939987519","https://openalex.org/W2979364224","https://openalex.org/W3026396438","https://openalex.org/W3119079778","https://openalex.org/W3163144570","https://openalex.org/W3196711847","https://openalex.org/W2949640357","https://openalex.org/W3209091012"],"abstract_inverted_index":{"Speech":[0],"emotion":[1,27,41],"recognition":[2,42],"is":[3,35],"the":[4,8,21,93,97,109,128],"task":[5],"of":[6,15,20,96,141],"recognizing":[7,47],"speaker's":[9],"emotional":[10],"state":[11],"given":[12],"a":[13,64,139],"recording":[14],"their":[16],"utterance.":[17],"While":[18],"most":[19],"current":[22],"approaches":[23,57],"focus":[24],"on":[25,92,118,122],"inferring":[26],"from":[28],"isolated":[29,123],"utterances,":[30],"we":[31,54,100,137],"argue":[32],"that":[33],"this":[34,52],"not":[36],"sufficient":[37],"to":[38,145],"achieve":[39],"conversational":[40],"(CER)":[43],"which":[44,107],"deals":[45],"with":[46,77],"emotions":[48],"in":[49,82],"conversations.":[50,148],"In":[51],"work,":[53],"propose":[55],"several":[56],"for":[58,72],"CER":[59,73],"by":[60,113,130],"treating":[61],"it":[62,76],"as":[63],"sequence":[65],"labeling":[66],"task.":[67],"We":[68,125],"investigated":[69],"transformer":[70,110,134],"architecture":[71],"and,":[74],"compared":[75],"ResNet-34":[78],"and":[79,85,120],"BiLSTM":[80],"architectures":[81],"both":[83],"contextual":[84],"contextless":[86],"scenarios":[87],"using":[88],"IEMOCAP":[89],"corpus.":[90],"Based":[91],"inner":[94],"workings":[95],"self-attention":[98],"mechanism,":[99],"proposed":[101],"DiverseCatAugment":[102],"(DCA),":[103],"an":[104,114,132],"augmentation":[105],"scheme,":[106],"improved":[108],"model":[111,135],"performance":[112,129],"absolute":[115],"3.3%":[116],"micro-f1":[117],"conversations":[119],"3.6%":[121],"utterances.":[124],"further":[126],"enhanced":[127],"introducing":[131],"interlocutor-aware":[133],"where":[136],"learn":[138],"dictionary":[140],"interlocutor":[142],"index":[143],"embeddings":[144],"exploit":[146],"diarized":[147]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}